© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 2148
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names and titles related to politics

    oai_token-act-pair · gpt-3.5-turbo

    references to specific political figures and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Proposition
    -0.70
     DV
    -0.69
     Sheep
    -0.68
     Fatal
    -0.67
    âĸ¬
    -0.67
     Pac
    -0.66
    âĸ¬âĸ¬
    -0.66
     Preservation
    -0.65
     Dominion
    -0.64
     Indie
    -0.64
    POSITIVE LOGITS
     Tillerson
    1.07
     memos
    0.99
     briefed
    0.95
    eln
    0.92
     briefings
    0.90
    uchin
    0.86
    lyak
    0.86
    arella
    0.86
     aide
    0.84
     confid
    0.83
    Activations Density 0.072%

    No Known Activations